Last active
March 10, 2026 14:14
-
-
Save ZiTAL/6f322f6778df83f7fe4b98f16bd15279 to your computer and use it in GitHub Desktop.
python: ollama rag example
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # based on: https://adityop.medium.com/building-rag-locally-02714f9d2007 | |
| from unstructured.partition.html import partition_html | |
| from urllib.request import urlopen | |
| from bs4 import BeautifulSoup | |
| import chromadb | |
| import ollama | |
| with urlopen( | |
| "<https://www.theringer.com/nba/2024/2/21/24074472/jump-ball-rules-strategy-chicanery-history>" | |
| ) as f: | |
| html = f.read().decode("utf-8") | |
| soup = BeautifulSoup(html, "html.parser") | |
| for tag in soup(["script", "style", "noscript"]): | |
| tag.decompose() | |
| html = soup.get_text() | |
| elements = partition_html(text=html) | |
| passages = [str(el) for el in elements if str(el).strip()] | |
| # passages to db | |
| chroma_client = chromadb.PersistentClient(path="./chroma_db") | |
| collection = chroma_client.get_or_create_collection(name="rag_cookbook_collection") | |
| if collection.count() == 0: | |
| collection.add(documents=passages, ids=[str(i) for i in range(len(passages))]) | |
| # prompt | |
| prompt_template = """Hi, please give me answer to the following question. Use the provided context below. | |
| In case you can't find answer in the article, just respond "I could not find the answer based on the context you provided." | |
| User question: {} | |
| Context: | |
| {} | |
| """ | |
| user_question = "Does NBA has a formal rule on how to do jump ball?" | |
| results = collection.query(query_texts=user_question, n_results=3) | |
| context = "\\n".join([f"{i+1}. {passage}" for i, passage in enumerate(results["documents"][0])]) | |
| prompt = f"{prompt_template.format(user_question, context)}" | |
| # model + result | |
| response = ollama.chat( | |
| model = "kimi-k2.5:cloud", | |
| messages = [ | |
| {"role": "user", "content": prompt} | |
| ], | |
| options = { | |
| "temperature": 0.0 | |
| } | |
| ) | |
| print(response["message"]["content"]) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| beautifulsoup4 | |
| chromadb | |
| unstructured | |
| ollama |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment